電気学会論文誌C(電子・情報・システム部門誌)
Online ISSN : 1348-8155
Print ISSN : 0385-4221
ISSN-L : 0385-4221
133 巻, 4 号
選択された号の論文の34件中1~34を表示しています
特集:新たなサービス社会に貢献する情報・システム技術
特集解説
特集論文
<システム・計測・制御>
  • 後藤 拓人, 矢島 敬士
    2013 年 133 巻 4 号 p. 699-705
    発行日: 2013/04/01
    公開日: 2013/04/01
    ジャーナル フリー
    Remote welfare services for caregivers have recently been offered in response to the recent increase in demand for care that has accompanied the aging of society. However, due to the often extended periods of caregiving involved, care consultations can sometimes lack cohesion unless information about the early stages of care are available. In order to address this issue, the whole history of communication between care experts and family members should be structured and visualized when remote welfare services are provided. We propose a form of remote consultation where care experts can offer coherent and efficient consultations using all available information, such as up-to-date information from “lifelogs” and past processes of care consultations obtained from the use of all historically available information.
  • 綿谷 亮, 岩井 大輔, 佐藤 宏介
    2013 年 133 巻 4 号 p. 706-712
    発行日: 2013/04/01
    公開日: 2013/04/01
    ジャーナル フリー
    More and more recent studies about emotion estimation have taken an ambient sensing approach, where users are monitored without constraining their bodies and consciousness of sensing systems. Few of them, however, are intended to audience emotions. The authors aimed to examine that audience emotions, which is difficult to be estimated by using only individual data, become to be estimated more easily by the ambient sensing of synchrony of multiple users. We developed the ambient sensing chair, which employs wireless sensors to determine the center of force of seated users, and designed an experiment on the audience watching soccer game on TV or technical presentation to examine the relationship between audience body sways and their emotions in a natural situation. As a result, synchrony could be well correlated to their excitation and boredom, which were not observed from individual data. These results indicate the possibility of the development of service marketing systems that evaluate TV contents and feedback systems that give notice of audience emotions to the presenter.
  • 浪江 宏宗, 中川 雅史
    2013 年 133 巻 4 号 p. 713-721
    発行日: 2013/04/01
    公開日: 2013/04/01
    ジャーナル フリー
    In the present study, we focused on the development of an indoor positioning system that is easy to use, portable and universally accessible. This system is capable of providing correct positional information anywhere indoors. Although GPS exhibits superior performance outdoors, there has been a considerable amount of research into indoor position determination by means of high-sensitivity GPS, pseudolites (GPS pseudo satellite), RFID (Radio Frequency IDentification) tags, and wireless LAN. However, the positioning rate, precision, radio signal interference, and cost performance levels of such technologies are still not high enough for general use, which is why they have not yet spread to pedestrian navigation systems. As a potential remedy, we created and examined an indoor positioning system using standard cellular phones with built-in GPS and infrared rays data communication functionalities, which are in widespread use in Japan. By this research, although indoor positioning of target precision 10 m required for pedestrian navigation has been realized in the comparatively narrow range, you still have to improve in respect of the rate of positioning.
<音声画像処理・認識>
<ソフトコンピューティング・学習>
  • Wan-Ling Li, Muhammad Hafidz Fazli bin Md Fauadi, Tomohiro Murata
    2013 年 133 巻 4 号 p. 730-739
    発行日: 2013/04/01
    公開日: 2013/04/01
    ジャーナル フリー
    This paper proposes a novel method of reactive scheduling of job processing for non-disruptive cell manufacturing systems (CMS) against unexpected machine breakdown occurrence. Reactive scheduling problem for reassigning pending jobs in CMS is formulated as a discrete optimization problem based on Integer Programming (IP) and effective solving method of BPSO-SA which consists of hybridized Binary Particle Swarm Optimization (BPSO) and Simulated Annealing (SA) methods is proposed to cope with time-critical recovery situation. BPSO is adopted to explore near optimal feasible solution of the discrete rescheduling problem and SA is used for the global optimization of locating a good approximation to the global optimum in a large search space. Numerical experiment demonstrates the effectiveness of the proposed model through case problems of non-disruptive jobs processing in CMS with unexpected machine breakdowns to seek for multiple objectives to minimize tardiness, number of intercellular movements, as well as maximizing cell load balancing. The results show that BPSO-SA provides a near optimal solution with significant reduction of calculation time compared to IP-based mathematical optimization method.
<情報システム,エレクトロニック・コマース>
<情報処理・ソフトウェア>
  • 和田 典子, 小坂 満隆
    2013 年 133 巻 4 号 p. 794-801
    発行日: 2013/04/01
    公開日: 2013/04/01
    ジャーナル フリー
    In response to ever increasing development size and complexity, many software development organizations have conducted various activities to improve the capabilities of software development. However, we have seen great variability in the outcomes of these activities, and that such variability has been attributed primarily to the skills and experiences of promoters of individual support activities. In this paper, we propose a methodology to software development support activities based on service value co-creation which contains embedded implicit knowledge of experienced promoters. This methodology was developed by viewing these support activities as services provided to the software organization, and by analyzing the relationship between support activities and outcomes from the perspective of service science. Finally, we demonstrate the validity of this methodology by analyzing three actual cases of software development capability improvement activities in light of this methodology.
  • 稲村 勝樹, 齊藤 旭, 岩村 惠市
    2013 年 133 巻 4 号 p. 802-815
    発行日: 2013/04/01
    公開日: 2013/04/01
    ジャーナル フリー
    Recently we need a new copyright protection system for a UGC (User Generated Content) in CGM (Consumer Generated Media) markets, which is generally made with re-use of existing content files. In this paper, we propose a new system that enables to pre-control editing contents with a digital signature from the viewpoint of editing control. Existent sanitizable signatures, which can only delete contents, are extended, and it is feasible to set up a work of editing as alteration, deletion and insertion including permission to edit contents. Therefore a content user can edit contents within the range of creator's permission.
特集研究開発レター
<メディア情報,ユーザ・インタフェース>
<情報システム,エレクトロニック・コマース>
論文
<システム・計測・制御>
<知能,ロボティクス>
  • 鳥井 昭宏, 山田 智弘, 上谷 亮介, 植田 明照, 道木 加絵
    2013 年 133 巻 4 号 p. 849-855
    発行日: 2013/04/01
    公開日: 2013/04/01
    ジャーナル フリー
    This paper describes an inchworm-type multi-degree-of-freedom stage, which consists of a platform, linear links and a base. The stage is based on a self-propelled Stewart-platform. We use six stacked-type piezoelectric actuators as the linear links. Six electromagnets are used in the stage. The electromagnets connect the linear links to the base and to the platform. This structure enables the Stewart-platfom to move on a surface by using the principle of an inchworm. The platform supported by the linear links is also operated by the principle of an inchworm, which enables the platform to rotate in the tilt directions. While the electromagnets fix the linear actuators on the base, the platform of the proposed stage realizes a precise multi-DOF motion. Design, principle, and control signals are described. The position and orientation of the moving platform is measured, and some experimental results indicate the feasibility of the proposed stage. The mechanism is effective for a precise positioning system which has a wide working area.
  • Siti Sendari, Shingo Mabu, Kotaro Hirasawa
    2013 年 133 巻 4 号 p. 856-863
    発行日: 2013/04/01
    公開日: 2013/04/01
    ジャーナル フリー
    This paper proposes Two-Stage Reinforcement Learning on Credit Branch Genetic Network Programming named GNP-TSRL-CB for mobile robots. The proposed method uses 2 kinds of Q-tables for sub node selection and credit branch selection, which has advantages of (1) determining an alternative function by using sub node selection and (2) skipping useless functions by using credit branch selection. It is clarified from simulation results that the adaptability mechanism of the proposed method can improve the performance compared with the conventional methods when the individuals of GNP-TSRL-CB are implemented in the dynamic environments like the sudden changes occur.
<音声画像処理・認識>
  • 吉田 隆之, 大槻 雅文, 中村 明生
    2013 年 133 巻 4 号 p. 864-875
    発行日: 2013/04/01
    公開日: 2013/04/01
    ジャーナル フリー
    We are developing a system that groups pedestrians and identifies relation. After detecting multiple persons from input image, the system observes their faces and groups them based on estimation of distance and conversation. Conversation is detected from face direction and mouth opening. To track feature points in the small and low-resolution face image, we use an Active Appearance Model (AAM). In addition, the system needs to observe not only faces used in the training but also ones of others to deal with unspecified persons. To cope with change in face orientation, we prepare three types of face models (left / front / right views). To reduce the amount of training data of AAM, we consider that only one face is used as base face to create the model. The face parts of eye and nose extracted from the created face model are randomly moved and deformed to fit on the face of others. Thus, the model obtained by learning from one person is applied to others and the feature tracking gets robustness. The system judges whether they make a conversation with Support Vector Machine (SVM) using face direction and mouth opening. Experimental results show effectiveness of the proposed method.
  • 成田 了, 大山 航, 若林 哲史, 木村 文隆
    2013 年 133 巻 4 号 p. 876-882
    発行日: 2013/04/01
    公開日: 2013/04/01
    ジャーナル フリー
    In this paper, we propose a new method for three dimensional rotation-free recognition of characters in scene. In the proposed method, we employ the Modified Quadratic Discriminant Function (MQDF) classifier trained with samples generated by three dimensional rotation process in a computer. We assume that when recognizing individual characters, considering three dimensional rotation can approximately handle the recognition of characters with perspective distortion. The results of the evaluation experiments using printed alphanumeric characters as an evaluation data set, consisting of approximately 600 samples per class for 62 character classes, show that the recognition rate is 99.34% for rotated characters while it is 99.59% for non rotated characters. We have empirically confirmed that the rotated characters given as the training data set do not negatively affect significantly to recognition of non rotated characters. Moreover, 813 characters extracted from 58 camera-captured scenes were correctly recognized and the feasibility of real world application of our method has been confirmed.
<情報システム,エレクトロニック・コマース>
  • 今奈良 祐紀, 鮫島 正樹, 秋吉 政徳
    2013 年 133 巻 4 号 p. 883-890
    発行日: 2013/04/01
    公開日: 2013/04/01
    ジャーナル フリー
    This paper addresses a problem to reconfigure a bug thread hierarchy in bug tracking systems. The bug thread hierarchy consists of dozens of bug threads that have dependent relationships each other, and the hierarchy is reconfigured when a recent bug thread is posted. Not only bug threads that have dependent relationships with the recent bug threads but also their dependent targets or sources are similar to the recent bug thread. In our proposed method, similarities with dependent targets and dependent sources are weighted to the similarity with the bug thread, and the bug thread that has the highest weighted similarity is identified to have a dependent relationship with a recent bug thread. The dependent direction is decided by the similarity with dependent targets and sources. As a result of the experiment, the hierarchy of the bug threads is reconfigured at a correct rate of 81%.
  • 坂入 威郎, 渡辺 昌志, 亀井 克之, 玉田 隆史, 後藤 幸夫, 瀬尾 和男
    2013 年 133 巻 4 号 p. 891-898
    発行日: 2013/04/01
    公開日: 2013/04/01
    ジャーナル フリー
    This paper presents the methods of dynamic load-balancing and control, which are applied for server-side rendering on Ajax-GIS. Ajax-GIS uses divided raster image tiles called for “tile” in order to keep light handling on web browser without some additional plug-in software. Server-side rendering is a technique for drawing images on the server side, which is effective to be able to solve the cross-browser issues and to reduce the client load. However when many clients request the Ajax-GIS server to render tile images, the server load will increase. In order to this issue, we propose the dynamic load-balancing and control by means of estimating server-side rendering request and monitoring server load. In experiments and evaluations of our proposed methods making use of an actual map data, we confirmed the effectiveness of our methods as comparing with conventional methods.
  • 今奈良 祐紀, 中島 大輔, 鮫島 正樹, 秋吉 政徳, 森久 博
    2013 年 133 巻 4 号 p. 899-905
    発行日: 2013/04/01
    公開日: 2013/04/01
    ジャーナル フリー
    This paper addresses a problem to identify risks in project plan documents written by project managers. Because some project managers express risks without negative words, the risk identification method by negative expressions is not sufficient to identify them. In this paper, we propose a risk identification method by automatic acquisition of risk expressions. The proposed method acquires the risk expressions from existing project plan documents based on the frequency of appearance in the sentences indicating risks. After the acquisition of the risk expressions, the proposed method extracts sentences including the expressions. From the extracted sentence, the proposed method identifies risks by comparing the sentence to each item of the checklist. In particular, the proposed method identifies the items corresponding to each extracted sentence by using related words. The experimental result shows that the proposed method identifies 81% of risks in the checklist and 45% of risks outside of the checklist on average.
研究開発レター
<メディア情報,ユーザ・インタフェース>
<音声画像処理・認識>
 
部門記事
 
feedback
Top